Multilingual Guidance for Unsupervised Linguistic Structure Prediction

Learn about multilingual approaches to unsupervised linguistic structure prediction in this hour-long research talk by Dipanjan Das from Carnegie Mellon University, presented at the Center for Language & Speech Processing at Johns Hopkins University. Explore how multilingual guidance can improve the prediction of linguistic structures without supervised training data, examining computational methods that leverage cross-lingual information to better understand and model language structure across different languages. Discover the theoretical foundations and practical applications of unsupervised learning techniques in natural language processing, with particular focus on how knowledge from multiple languages can inform and enhance structural prediction tasks in computational linguistics.